Rishikesh (ऋषिकेश)

@seungwonpark checkout first sample : https://drive.google.com/drive/folders/1fPjLwMORsfilwPS9EAXUR_5ZKjUWbaIA?usp=sharing `Note: This is non GTA sample using nvidia's tacotron2`

@seungwonpark official repo [melgan](https://github.com/descriptinc/melgan-neurips)

Just for Information: New paper on [Parallel WaveGAN](https://arxiv.org/pdf/1910.11480.pdf). The best part is it's fast, lightweight(1.4 M parameters only) and specially designed for TTS engine. ``` We propose Parallel WaveGAN, a...

@seungwonpark give a look at this paper: https://arxiv.org/pdf/2005.05106.pdf . Seems very promising, use two different model strategies.

@seungwonpark Hope you are doing well ! I have coded Multi-band MelGAN paper and uses this repo as a base. Please give it a look https://github.com/rishikksh20/melgan . Though I just...

@xuexidi it doesn't give good result, I had trained model around 1.5 Million step but normal mel training gives better result than GTA. Though one option which I havn't tried...

@xuexidi it doesn't matter choose any pre-processing (mel-extraction) and use the same for both TTS and melgan. The mels on which TTS trained always be same as on which melgan...

No, it's not just follow this link : https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5

@dunky11 Have look at this Soft-DTW implementation https://github.com/google-research/soft-dtw-divergences ?

@yutinyang error occur in which line number ?